Spiking neural networks (SNNs) process time-series data via internal event-driven neural dynamics whose energy consumption depends on the number of spikes exchanged between neurons over the course of the input presentation. In typical implementations of an SNN classifier, decisions are produced after the entire input sequence has been processed, resulting in latency and energy consumption levels that are fairly uniform across inputs. Recently introduced delay-adaptive SNNs tailor the inference latency -- and, with it, the energy consumption -- to the difficulty of each example, by producing an early decision when the SNN model is sufficiently ``confident''. In this paper, we start by observing that, as an SNN processes input samples, its classification decisions tend to be first under-confident and then over-confident with respect to the decision's ground-truth, unknown, test accuracy. This makes it difficult to determine a stopping time that ensures a desired level of accuracy. To address this problem, we introduce a novel delay-adaptive SNN-based inference methodology that, wrapping around any pre-trained SNN classifier, provides guaranteed reliability for the decisions produced at input-dependent stopping times. The approach entails minimal added complexity as compared to the underlying SNN, requiring only thresholding and counting operations at run time, and it leverages tools from conformal prediction (CP).

翻译：脉冲神经网络（SNN）通过内部事件驱动的神经动力学处理时序数据，其能量消耗取决于输入呈现过程中神经元之间交换的脉冲数量。在典型的SNN分类器实现中，决策是在整个输入序列处理完毕后做出的，导致延迟和能量消耗水平在不同输入间大致均匀。近期提出的延迟自适应SNN通过根据每个样本的难度调整推理延迟（以及随之而来的能量消耗），在SNN模型足够"自信"时提前做出决策。本文首先观察到：随着SNN处理输入样本，其分类决策往往先呈现自信不足、后呈现过度自信的状态（相对于决策的真实未知测试精度）。这使得难以确定能确保期望精度的停止时间。为解决该问题，我们提出一种新颖的基于延迟自适应SNN的推理方法，该方法可封装任何预训练的SNN分类器，为基于输入依赖的停止时间所做出的决策提供可靠性保证。与底层SNN相比，该方法的额外复杂度极低，运行时仅需阈值判断和计数操作，并利用了共形预测（CP）工具。